Downloads · 30 days
39
34% of all-time downloads
gemma-4-E2B-it-Q4_0-lean-GGUF
InterstellarCG/gemma-4-E2B-it-Q4_0-lean-GGUF
gemma-4-E2B-it-Q4_0-lean-GGUF is a machine learning model from InterstellarCG. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as gemma.
Requant of gemma-4-E2B-it with every large tensor forced to Q40, including the tied token embedding / output head and the per-layer embedding table (the standard Q40 recipe leaves those at Q6K, costing ~20% generation…
All-time downloads
114
Public
Repo size
2.7 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf2.7 GB · 100%
At a glance
- License
- gemma
- Access
- Public
- Created
- Jul 20, 2026
- Updated
- Jul 20, 2026
- SHA
- 6155b4eb
Base models
Model card
From the Hugging Face model README
Gemma 4 E2B it — "lean" Q4_0 GGUF
Requant of gemma-4-E2B-it with every large tensor forced to Q4_0, including the tied token embedding / output head and the per-layer embedding table (the standard Q4_0 recipe leaves those at Q6_K, costing ~20% generation speed on memory-bandwidth-limited hardware).
- 2.65 GB vs 3.36 GB standard Q4_0; ~20% faster token generation on iGPU/CPU systems.
- Made with llama.cpp b9966
llama-quantize --allow-requantize --token-embedding-type q4_0 --output-tensor-type q4_0from the official lmstudio-community Q4_K_M. - Usage subject to the Gemma Terms of Use.
- License
- gemma
- Created
- Jul 20, 2026
- Updated
- Jul 20, 2026